高级检索

激光诱导击穿光谱结合PCA-BP算法的荧光粉检测与识别

Laser-induced breakdown spectroscopy combined with PCA-BP algorithm for phosphor detection and recognition

  • 摘要: 为了提高电子废弃物的分类回收利用效率,基于激光诱导击穿光谱技术和主成分分析(PCA)算法与反向传播(BP)算法, 建立了一种电子荧光粉检测与识别系统来验证该系统的可靠性。以3种不同型号的荧光粉(CRT-B,P43和P47)为例,采用该系统获取荧光粉样品在200 nm~890 nm范围内的激光诱导击穿光谱数据,完成了对光谱谱线校正和元素标定。结果表明,荧光粉CRT-B富含元素Zn、Al,P43富含元素Gd,P47富含元素Y、Si,P47中还检测到微量元素Ce;利用PCA算法分析光谱数据,前3个主成分的贡献率高达99.769%,3种荧光粉在空间中可以被清晰地分开;建立的PCA-BP神经网络模型对CRT-B、P43及P47荧光粉的识别率分别为99.8%、100%和100%。该研究结果对工业生产生活中电子废弃物的快速检测和回收利用是有帮助的。

     

    Abstract: In order to improve the classification and recycling efficiency of electronic waste, a detection and identification system of electronic phosphor based on laser-induced breakdown spectroscopy and principal components analysis(PCA) algorithm & back propagation(BP) algorithm was established. In order to verify the reliability of the system, three different models of phosphor (CRT-B, P43 and P47) were taken as examples. The system was used to obtain the laser-induced breakdown spectral data of phosphor samples in the range of 200 nm~890 nm, and the spectral line calibration and element calibration were completed. The results showe that the phosphor CRT-B is rich in Zn and Al, P43 is rich in Gd, P47 is rich in Y and Si, and trace element Ce is also detected in the phosphor P47. The results show that the contribution rate of the first three principal components is as high as 99.769%, and the three phosphors can be clearly separated in space. The recognition rates of CRT-B, P43 and P47 phosphor by PCA-BP are 99.8%, 100% and 100%, respectively. The results of this study are helpful for the rapid detection and recycling of electronic waste in industrial production and life.

     

/

返回文章
返回